{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:35:37Z","timestamp":1778081737002,"version":"3.51.4"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319105833","type":"print"},{"value":"9783319105840","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-10584-0_20","type":"book-chapter","created":{"date-parts":[[2014,8,14]],"date-time":"2014-08-14T11:40:08Z","timestamp":1408016408000},"page":"297-312","source":"Crossref","is-referenced-by-count":595,"title":["Simultaneous Detection and Segmentation"],"prefix":"10.1007","author":[{"given":"Bharath","family":"Hariharan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pablo","family":"Arbel\u00e1ez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ross","family":"Girshick","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jitendra","family":"Malik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Arbel\u00e1ez, P., Pont-Tuset, J., Barron, J., Marques, F., Malik, J.: Multiscale combinatorial grouping. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.49"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Arbel\u00e1ez, P., Hariharan, B., Gu, C., Gupta, S., Malik, J.: Semantic segmentation using regions and parts. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248077"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Boix, X., Gonfaus, J.M., van de Weijer, J., Bagdanov, A.D., Serrat, J., Gonz\u00e0lez, J.: Harmony potentials. IJCV 96(1) (2012)","DOI":"10.1007\/s11263-011-0449-8"},{"key":"20_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1007\/978-3-642-15567-3_13","volume-title":"Computer Vision \u2013 ECCV 2010","author":"L. Bourdev","year":"2010","unstructured":"Bourdev, L., Maji, S., Brox, T., Malik, J.: Detecting people using mutually consistent poselet activations. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol.\u00a06316, pp. 168\u2013181. Springer, Heidelberg (2010)"},{"key":"20_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1007\/978-3-642-33786-4_32","volume-title":"Computer Vision \u2013 ECCV 2012","author":"J. Carreira","year":"2012","unstructured":"Carreira, J., Caseiro, R., Batista, J., Sminchisescu, C.: Semantic segmentation with second-order pooling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol.\u00a07578, pp. 430\u2013443. Springer, Heidelberg (2012)"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Sminchisescu, C.: Constrained parametric min-cuts for automatic object segmentation. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540063"},{"key":"20_CR7","unstructured":"Dai, Q., Hoiem, D.: Learning to localize detected objects. In: CVPR (2012)"},{"key":"20_CR8","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)"},{"key":"20_CR9","unstructured":"Deng, J., Berg, A., Satheesh, S., Su, H., Khosla, A., Fei-Fei, L.: ImageNet Large Scale Visual Recognition Competition 2012 (ILSVRC 2012) (2012), \n                    \n                      http:\/\/www.image-net.org\/challenges\/LSVRC\/2012\/"},{"key":"20_CR10","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: Decaf: A deep convolutional activation feature for generic visual recognition. arXiv preprint arXiv:1310.1531 (2013)"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The Pascal Visual Object Classes (VOC) Challenge. IJCV 88(2) (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Farabet, C., Couprie, C., Najman, L., LeCun, Y.: Learning hierarchical features for scene labeling. TPAMI 35(8) (2013)","DOI":"10.1109\/TPAMI.2012.231"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. TPAMI 32(9) (2010)","DOI":"10.1109\/TPAMI.2009.167"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Fidler, S., Mottaghi, R., Yuille, A., Urtasun, R.: Bottom-up segmentation for top-down detection. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.423"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics 36(4) (1980)","DOI":"10.1007\/BF00344251"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbelaez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"20_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1007\/978-3-642-33712-3_25","volume-title":"Computer Vision \u2013 ECCV 2012","author":"D. Hoiem","year":"2012","unstructured":"Hoiem, D., Chodpathumwan, Y., Dai, Q.: Diagnosing error in object detectors. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol.\u00a07574, pp. 340\u2013353. Springer, Heidelberg (2012)"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Jia, Y.: Caffe: An open source convolutional architecture for fast feature embedding (2013), \n                    \n                      http:\/\/caffe.berkeleyvision.org\/","DOI":"10.1145\/2647868.2654889"},{"key":"20_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/978-3-642-33885-4_30","volume-title":"Computer Vision \u2013 ECCV 2012. Workshops and Demonstrations","author":"B.-S. Kim","year":"2012","unstructured":"Kim, B.-S., Sun, M., Kohli, P., Savarese, S.: Relating things and stuff by high-order potential modeling. In: Fusiello, A., Murino, V., Cucchiara, R. (eds.) ECCV 2012 Ws\/Demos, Part III. LNCS, vol.\u00a07585, pp. 293\u2013304. Springer, Heidelberg (2012)"},{"key":"20_CR21","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"20_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1007\/978-3-642-15561-1_31","volume-title":"Computer Vision \u2013 ECCV 2010","author":"L. Ladick\u00fd","year":"2010","unstructured":"Ladick\u00fd, L., Sturgess, P., Alahari, K., Russell, C., Torr, P.H.S.: What, where and how many? Combining object detectors and CRFs. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol.\u00a06314, pp. 424\u2013437. Springer, Heidelberg (2010)"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Computation 1(4) (1989)","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2) (2004)","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Mottaghi, R.: Augmenting deformable part models with irregular-shaped object patches. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248044"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Jawahar, C., Zisserman, A.: The truth about cats and dogs. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126398"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"van de Sande, K.E., Uijlings, J.R., Gevers, T., Smeulders, A.W.: Segmentation as selective search for object recognition. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"20_CR28","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: Integrated recognition, localization and detection using convolutional networks. In: ICLR (2014)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Sermanet, P., Kavukcuoglu, K., Chintala, S., LeCun, Y.: Pedestrian detection with unsupervised multi-stage feature learning. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.465"},{"key":"20_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/11744023_1","volume-title":"Computer Vision \u2013 ECCV 2006","author":"J. Shotton","year":"2006","unstructured":"Shotton, J., Winn, J.M., Rother, C., Criminisi, A.: TextonBoost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol.\u00a03951, pp. 1\u201315. Springer, Heidelberg (2006)"},{"key":"20_CR31","unstructured":"Tighe, J., Niethammer, M., Lazebnik, S.: Scene parsing with object instances and occlusion handling. In: ECCV (2010)"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Yang, Y., Hallman, S., Ramanan, D., Fowlkes, C.C.: Layered object models for image segmentation. TPAMI 34(9) (2012)","DOI":"10.1109\/TPAMI.2011.208"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2014"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-10584-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T09:49:14Z","timestamp":1575280154000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-10584-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319105833","9783319105840"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-10584-0_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}